INDEX

Explanations

curiosity and discovery

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-1.38

edade

-1.29

 Лон

-1.27

 köpa

-1.23

龶

-1.21

を行いました

-1.19

 avenida

-1.17

だよ

-1.16

межу

-1.16

怍

-1.14

POSITIVE LOGITS

なぜか

1.54

1.41

 already

1.39

ate

1.38

何故

1.36

claimers

1.34

ين

1.34

ender

1.31

 offizielle

1.30

sie

1.28

Activations Density 0.036%